telegram-field-bot

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill directly ingests and processes arbitrary user-generated Telegram content (see SKILL.md: handle_photo, handle_text, handle_group_message and the n8n "Process Photo" node / generate_daily_report which call an LLM to analyze caption/text/photo and JSON reports), so untrusted third-party messages/photos are read and used to drive LLM analysis and downstream actions.